Unique ID: 2015014

Division: Coordination administrative & big data
Issue Date: February 13th 2019
Last modified: February 22nd 2019
Collaborative

Using scanner data for consumer prices

Using scanner data for consumer prices.

Using very detailed scanner data from the major supermarket chains as input for monthly consumer prices (national CPI and very soon European HICP), particularly for food and personal hygiene products.

Project Objective:

For the production of statistics

Project Outcomes:

More cost-efficient, much more detailed and equally timely food consumer price information compared to traditional method (persons recording sample prices in sample sales outlets).

Statistical Area

Price

Project Sources
Project Sources
Type Of Institution: National statistical office
Big Data Source: Scanner data
Region: Europe & Central Asia
Country Area: Belgium
Id Country Regional: country
Partnerships
Partnerships
Other Partners: Other
Partnership Comments: Food retail companies (supermarket chains).
Accessing Data
Accessing Data
Data Access Rights: Only for this project
Data Access Comments: Only objective, at the moment, is calculation of consumer price indices.
Data Coverage
Data Coverage
Data Coverage: All available data
Coverage Geo Pop: Whole country / high % of market
Cost Implication: Free
Coverage Period: Since January 2015, start of statistical production stage.
Project Details
Project Details
Frequency Comments: Data come in on a weekly basis with each incoming dataset, for each of the three providers, of a size of approximately 1.5 GB (about 20 GB per month and 240 GB annually).
Data Quality
Data Quality
Quality Framework: Quality of output statistics
Quality Aspects Evaluated: Privacy and Security, Completeness, Usability, Time Factors, Accuracy, including selectivity
Validation Comments: Data are prices for specific items, identical to previous data available (just a lot more), no conceptual or interpretation issues.
Quality Framework Comments: Quality of source/input: prices from the datasets have been validated against manually collected prices, old method; turnover data have been verified for consistency over time. Quality of output statistics: simulations on scanner data have been compared with manual price collection; differences between the two have been examined in detail.
Methodology
Methodology
Methods Used: Traditional statistical methods
Methods Comments: Regular CPI calculations using new source.
Technologies
Technologies
Technologies: Relational database
Other
Other
Income Level: High-income
Iso: BE
Timeframe To Produce Indicator: NA
Frequency Comments: Data come in on a weekly basis with each incoming dataset, for each of the three providers, of a size of approximately 1.5 GB (about 20 GB per month and 240 GB annually).
Write Your Own Review
You're reviewing:Using scanner data for consumer prices
Your Rating